AI Article Synopsis
- The study aims to evaluate how machine learning and imaging techniques can predict postoperative risk factors in cervical cancer patients, such as lymph node metastasis and muscle invasion.
- Researchers analyzed data from 180 patients, dividing them into training and validation groups to develop predictive models using imaging and clinical parameters.
- The results showed that nomograms created with these methods outperformed traditional MRI assessments in predicting various risk factors, highlighting their potential as effective tools in cervical cancer management.
Article Abstract
Rationale And Objectives: To investigate the value of machine learning-based radiomics, intravoxel incoherent motion (IVIM) diffusion-weighted imaging and its combined model in predicting the postoperative risk factors of parametrial infiltration (PI), lymph node metastasis (LNM), deep muscle invasion (DMI), lymph-vascular space invasion (LVSI), pathological type (PT), differentiation degree (DD), and Ki-67 expression level in patients with cervical cancer.
Materials And Methods: The data of 180 patients with cervical cancer were retrospectively analyzed and randomized 2:1 into a training and validation group. The IVIM-DWI and radiomics parameters of primary lesions were measured in all patients. Seven machine learning methods were used to calculate the optimal radiomics score (Rad-score), which was combined with IVIM-DWI and clinical parameters to construct nomograms for predicting the risk factors of cervical cancer, with internal and external validation.
Results: The diagnostic efficacy of the nomograms based on clinical and imaging parameters was significantly better than MRI assessment alone. The area under the curve (AUC) of nomograms and MRI for the assessment of PI, LNM, and DMI were 0.981 vs 0.868, 0.848 vs 0.639, and 0.896 vs 0.780, respectively. Nomograms also performed well in the assessment of LVSI, PT, DD, and Ki-67 expression levels, with AUC of 0.796, 0.854, 0.806, 0.839 and 0.840, 0.856, 0.810, 0.832 in the training and validation groups.
Conclusion: Machine learning-based nomograms can serve as a useful tool for assessing postoperative risk factors in patients with cervical cancer.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.acra.2023.09.031 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Epidemiologic Investigation of Protozoa and Soil-Transmitted Helminths in Starr County, Texas.
Am J Trop Med Hyg
January 2025
Department of Pediatrics, National School of Tropical Medicine, Section of Tropical Medicine, Baylor College of Medicine, Houston, Texas.
The burden of pathogenic enteric protozoa and soil-transmitted helminths among impoverished populations living on the Texas-Mexico border is unclear. We conducted a cross-sectional study on an ongoing longitudinal cohort of 616 adults residing in Starr County, Texas. A total of 359 adults were screened for four protozoa and five soil-transmitted helminths by using real-time polymerase chain reaction.
View Article and Find Full Text PDFAn exploratory survey assessing the determinants of heat stress and heat strain in the Canadian mining industry from the worker's perspective.
J Occup Environ Hyg
January 2025
Human and Environmental Physiology Research Unit, School of Human Kinetics, Faculty of Health Sciences, University of Ottawa, Ottawa, Ontario, Canada.
With mines extending deeper and rising surface temperatures, workers are exposed to hotter environments. This study aimed to characterize heat stress and strain in the Canadian mining industry and evaluate the utility of the Heat Strain Score Index (HSSI), combined with additional self-reported adverse health outcomes. An exploratory web-based survey was conducted among workers ( = 119) in the Canadian mining industry.
View Article and Find Full Text PDFLong-Term Impact of Using Mobile Phones and Playing Computer Games on the Brain Structure and the Risk of Neurodegenerative Diseases: Large Population-Based Study.
J Med Internet Res
January 2025
Department of Neurology, West China Hospital, Sichuan University, Chengdu, China.
Background: Despite the increasing popularity of electronic devices, the longitudinal effects of daily prolonged electronic device usage on brain health and the aging process remain unclear.
Objective: The aim of this study was to investigate the impact of the daily use of mobile phones/computers on the brain structure and the risk of neurodegenerative diseases.
Methods: We used data from the UK Biobank, a longitudinal population-based cohort study, to analyze the impact of mobile phone use duration, weekly usage time, and playing computer games on the future brain structure and the future risk of various neurodegenerative diseases, including all-cause dementia (ACD), Alzheimer disease (AD), vascular dementia (VD), all-cause parkinsonism (ACP), and Parkinson disease (PD).
Self-Management Strategies for Low Back Pain Among Horticulture Workers: Protocol for a Type II Hybrid Effectiveness-Implementation Study.
JMIR Res Protoc
January 2025
Department of Pediatrics, School of Medicine, University of Virginia, Charlottesville, VA, United States.
Background: Low back pain (LBP) is highly prevalent and disabling, especially in agriculture sectors. However, there is a gap in LBP prevention and intervention studies in these physically demanding occupations, and to date, no studies have focused on horticulture workers. Given the challenges of implementing interventions for those working in small businesses, self-management offers an attractive and feasible option to address work-related risk factors and manage LBP.
View Article and Find Full Text PDFThe Clinicians' Guide to Large Language Models: A General Perspective With a Focus on Hallucinations.
Interact J Med Res
January 2025
Medical Directorate, Lausanne University Hospital, Lausanne, Switzerland.
Large language models (LLMs) are artificial intelligence tools that have the prospect of profoundly changing how we practice all aspects of medicine. Considering the incredible potential of LLMs in medicine and the interest of many health care stakeholders for implementation into routine practice, it is therefore essential that clinicians be aware of the basic risks associated with the use of these models. Namely, a significant risk associated with the use of LLMs is their potential to create hallucinations.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!